Ctrl+K

Final specimen mapping

Final specimen mapping#

Kasumi1 naive#

Hide code cell source 
import pandas as pd
import sys
sys.path.append('../')

from source.bokeh_plots import *
from source.data_visualization import *
output_notebook()

mount = '/mnt/e/'
input_path = mount + 'MethylScore_v2/Processed_Data/'

test_sample_name = 'kasumi1_naive'
df_nanopore = pd.read_pickle(input_path + test_sample_name + '_processed.pkl')

plot_linked_scatters(df_nanopore, table=False, test_sample=test_sample_name,
                     xaxis = "PaCMAP 1 of 2", yaxis = "PaCMAP 2 of 2",
                     cols=['WHO 2022 Diagnosis'])

df_nanopore.iloc[-1:,:][['AML Epigenomic Risk', 'AML Epigenomic Risk P(High Risk)',\
    'AL Epigenomic Phenotype', f'P({df_nanopore.iloc[-1:,:]["AL Epigenomic Phenotype"].item()})']]
Hide code cell output
Loading BokehJS ...
AML Epigenomic Risk AML Epigenomic Risk P(High Risk) AL Epigenomic Phenotype P(AML with ETV6 fusion)
kasumi1_naive Low 0.249 AML with ETV6 fusion 0.952

Note

Though we generate the PaCMAP embedding in 2 dimensions (x and y axis) for visualization purposes, the predictive models were trained using 5 dimensions, so the following plots show the first two dimensions out of 5.

Hide code cell source 
plot_linked_scatters(df_nanopore, table=False, test_sample=test_sample_name,
                     xaxis = "PaCMAP 1 of 5", yaxis = "PaCMAP 2 of 5",
                     x_range=(-25, 25), y_range=(-25, 25),
                     cols=['WHO 2022 Diagnosis'])

df_nanopore.iloc[-1:,:][['AML Epigenomic Risk', 'AML Epigenomic Risk P(High Risk)',\
    'AL Epigenomic Phenotype', f'P({df_nanopore.iloc[-1:,:]["AL Epigenomic Phenotype"].item()})']]
Hide code cell output
AML Epigenomic Risk AML Epigenomic Risk P(High Risk) AL Epigenomic Phenotype P(AML with ETV6 fusion)
kasumi1_naive Low 0.249 AML with ETV6 fusion 0.952

Kasumi1 + 0.7uM Decitabine harvested 72h#

Hide code cell source 
test_sample_name = 'kasumi1_07deci'
df_nanopore = pd.read_pickle(input_path + test_sample_name + '_processed.pkl')

plot_linked_scatters(df_nanopore, table=False, test_sample=test_sample_name,
                     xaxis = "PaCMAP 1 of 5", yaxis = "PaCMAP 2 of 5",
                     x_range=(-25, 25), y_range=(-25, 25),
                     cols=['WHO 2022 Diagnosis'])

df_nanopore.iloc[-1:,:][['AML Epigenomic Risk', 'AML Epigenomic Risk P(High Risk)',\
    'AL Epigenomic Phenotype', f'P({df_nanopore.iloc[-1:,:]["AL Epigenomic Phenotype"].item()})']]
Hide code cell output
AML Epigenomic Risk AML Epigenomic Risk P(High Risk) AL Epigenomic Phenotype P(AML with mutated NPM1)
kasumi1_07deci High 0.753 AML with mutated NPM1 0.408

The confidence of the model droppped significantly with hypomethylating agent exposure (40.8% confidence).

UF HemBank 1829#

Hide code cell source 
test_sample_name = 'uf_hembank_1829'
df_nanopore = pd.read_pickle(input_path + test_sample_name + '_processed.pkl')

plot_linked_scatters(df_nanopore, table=False, test_sample=test_sample_name,
                     xaxis = "PaCMAP 1 of 5", yaxis = "PaCMAP 2 of 5",
                     x_range=(-25, 25), y_range=(-25, 25),
                     cols=['WHO 2022 Diagnosis'])

df_nanopore.iloc[-1:,:][['AML Epigenomic Risk', 'AML Epigenomic Risk P(High Risk)',\
    'AL Epigenomic Phenotype', f'P({df_nanopore.iloc[-1:,:]["AL Epigenomic Phenotype"].item()})']]
Hide code cell output
AML Epigenomic Risk AML Epigenomic Risk P(High Risk) AL Epigenomic Phenotype P(AML with t(v;11q23); KMT2A-r)
uf_hembank_1829 High 0.724 AML with t(v;11q23); KMT2A-r 0.976

UF HemBank 1830#

Hide code cell source 
test_sample_name = 'uf_hembank_1830'
df_nanopore = pd.read_pickle(input_path + test_sample_name + '_processed.pkl')

plot_linked_scatters(df_nanopore, table=False, test_sample=test_sample_name,
                     xaxis = "PaCMAP 1 of 5", yaxis = "PaCMAP 2 of 5",
                     x_range=(-25, 25), y_range=(-25, 25),
                     cols=['WHO 2022 Diagnosis'])

df_nanopore.iloc[-1:,:][['AML Epigenomic Risk', 'AML Epigenomic Risk P(High Risk)',\
    'AL Epigenomic Phenotype', f'P({df_nanopore.iloc[-1:,:]["AL Epigenomic Phenotype"].item()})']]
Hide code cell output
AML Epigenomic Risk AML Epigenomic Risk P(High Risk) AL Epigenomic Phenotype P(AML with t(v;11q23); KMT2A-r)
uf_hembank_1830 High 0.881 AML with t(v;11q23); KMT2A-r 0.974

UF HemBank 1831#

Hide code cell source 
test_sample_name = 'uf_hembank_1831'
df_nanopore = pd.read_pickle(input_path + test_sample_name + '_processed.pkl')

plot_linked_scatters(df_nanopore, table=False, test_sample=test_sample_name,
                     xaxis = "PaCMAP 1 of 5", yaxis = "PaCMAP 2 of 5",
                     x_range=(-25, 25), y_range=(-25, 25),
                     cols=['WHO 2022 Diagnosis'])

df_nanopore.iloc[-1:,:][['AML Epigenomic Risk', 'AML Epigenomic Risk P(High Risk)',\
    'AL Epigenomic Phenotype', f'P({df_nanopore.iloc[-1:,:]["AL Epigenomic Phenotype"].item()})']]
Hide code cell output
AML Epigenomic Risk AML Epigenomic Risk P(High Risk) AL Epigenomic Phenotype P(Otherwise-Normal Control)
uf_hembank_1831 Low 0.354 Otherwise-Normal Control 0.991

UF HemBank 1832#

Hide code cell source 
test_sample_name = 'uf_hembank_1832'
df_nanopore = pd.read_pickle(input_path + test_sample_name + '_processed.pkl')

plot_linked_scatters(df_nanopore, table=False, test_sample=test_sample_name,
                     xaxis = "PaCMAP 1 of 5", yaxis = "PaCMAP 2 of 5",
                     x_range=(-25, 25), y_range=(-25, 25),
                     cols=['WHO 2022 Diagnosis'])

df_nanopore.iloc[-1:,:][['AML Epigenomic Risk', 'AML Epigenomic Risk P(High Risk)',\
    'AL Epigenomic Phenotype', f'P({df_nanopore.iloc[-1:,:]["AL Epigenomic Phenotype"].item()})']]
Hide code cell output
AML Epigenomic Risk AML Epigenomic Risk P(High Risk) AL Epigenomic Phenotype P(Otherwise-Normal Control)
uf_hembank_1832 Low 0.149 Otherwise-Normal Control 0.991

UF HemBank 1841#

Hide code cell source 
test_sample_name = 'uf_hembank_1841'
df_nanopore = pd.read_pickle(input_path + test_sample_name + '_processed.pkl')

plot_linked_scatters(df_nanopore, table=False, test_sample=test_sample_name,
                     xaxis = "PaCMAP 1 of 5", yaxis = "PaCMAP 2 of 5",
                     x_range=(-25, 25), y_range=(-25, 25),
                     cols=['WHO 2022 Diagnosis'])

df_nanopore.iloc[-1:,:][['AML Epigenomic Risk', 'AML Epigenomic Risk P(High Risk)',\
    'AL Epigenomic Phenotype', f'P({df_nanopore.iloc[-1:,:]["AL Epigenomic Phenotype"].item()})']]
Hide code cell output
AML Epigenomic Risk AML Epigenomic Risk P(High Risk) AL Epigenomic Phenotype P(Otherwise-Normal Control)
uf_hembank_1841 High 0.678 Otherwise-Normal Control 0.988

UF HemBank 1852#

Hide code cell source 
test_sample_name = 'uf_hembank_1852'
df_nanopore = pd.read_pickle(input_path + test_sample_name + '_processed.pkl')

plot_linked_scatters(df_nanopore, table=False, test_sample=test_sample_name,
                     xaxis = "PaCMAP 1 of 5", yaxis = "PaCMAP 2 of 5",
                     x_range=(-25, 25), y_range=(-25, 25),
                     cols=['WHO 2022 Diagnosis'])

df_nanopore.iloc[-1:,:][['AML Epigenomic Risk', 'AML Epigenomic Risk P(High Risk)',\
    'AL Epigenomic Phenotype', f'P({df_nanopore.iloc[-1:,:]["AL Epigenomic Phenotype"].item()})']]
Hide code cell output
AML Epigenomic Risk AML Epigenomic Risk P(High Risk) AL Epigenomic Phenotype P(AML with NUP98-fusion)
uf_hembank_1852 High 0.786 AML with NUP98-fusion 0.83
Contents